Anthropic 如何用 Claude 造 Claude：大脑与手分离
原标题：How Anthropic ships Claude with Claude: Separating the Brain from the Hands
AI 摘要
Latent Space 播客深入介绍了 Anthropic 如何用 Claude 构建 Claude，重点讨论 Opus 5.5 发布同时伴随的 API 变更，以及 Managed Agents 中「大脑与手」分离的架构：会话日志与 harness 同执行代码的沙箱解耦，从而提升可靠性、降低延迟，并让沙箱内不持有服务凭证以增强安全。节目还提到 Anthropic 已提交 S-1、预计两周内以 2 万亿美元估值 IPO，并讨论了记忆、多智能体工作流与评估实践。
正文节选
As we learned from the Anthropic S-1 filings yesterday, the lab has some of the highest revenue and research efficiency in human history, particularly with -126% loss to 19% GAAP profit turnaround in the last year. The company credits this to their two core loops: Improvement and Investment: Today we go inside how Anthropic works. Now the dust has settled on Opus 5.5 and it has lasted a month as the generally accepted #1 LLM in the world, we dive into its launch, and how Anthropic ships Claude w